D-Sweep: Using Profile Snapping for 3D Object Extraction from Single Image

2014 ◽  
pp. 39-50 ◽  
Author(s):  
Pan Hu ◽  
Hongming Cai ◽  
Fenglin Bu
Keyword(s):  
Object Extraction ◽  
Single Image ◽  
3D Object

scholarly journals Pixel2point: 3D Object Reconstruction From a Single Image Using CNN and Initial Sphere

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 110-121
Author(s):  
Ahmed J. Afifi ◽  
Jannes Magnusson ◽  
Toufique A. Soomro ◽  
Olaf Hellwich
Keyword(s):  
Single Image ◽  
Object Reconstruction ◽  
3D Object ◽  
3D Object Reconstruction

scholarly journals Using Curvilinear Features in Focus for Registering a Single Image to a 3D Object

2019 ◽  
Vol 28 (9) ◽  
pp. 4429-4443 ◽  
Author(s):  
Hatem A. Rashwan ◽  
Sylvie Chambon ◽  
Pierre Gurdjos ◽  
Geraldine Morin ◽  
Vincent Charvillat
Keyword(s):  
Single Image ◽  
3D Object ◽  
Curvilinear Features

scholarly journals Attention-based 3D Object Reconstruction from a Single Image

2020 ◽  
Author(s):  
Andrey Salvi ◽  
Nathan Gavenski ◽  
Eduardo Pooch ◽  
Felipe Tasoniero ◽  
Rodrigo Barros
Keyword(s):  
Single Image ◽  
Object Reconstruction ◽  
3D Object ◽  
3D Object Reconstruction

scholarly journals IAFA: Instance-Aware Feature Aggregation for 3D Object Detection from a Single Image

2021 ◽  
pp. 417-435
Author(s):  
Dingfu Zhou ◽  
Xibin Song ◽  
Yuchao Dai ◽  
Junbo Yin ◽  
Feixiang Lu ◽  
...  
Keyword(s):  
Object Detection ◽  
Single Image ◽  
3D Object ◽  
Feature Aggregation ◽  
3D Object Detection

scholarly journals Class-aware single image to 3D object translational autoencoder

2020 ◽  
Vol 14 (13) ◽  
pp. 3046-3053
Author(s):  
Ceren Guzel Turhan ◽  
Hasan Sakir Bilge
Keyword(s):  
Single Image ◽  
3D Object

scholarly journals Improved Multiview Decomposition for Single-Image High-Resolution 3D Object Reconstruction

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Jiansheng Peng ◽  
Kui Fu ◽  
Qingjin Wei ◽  
Yong Qin ◽  
Qiwen He
Keyword(s):  
High Resolution ◽  
Depth Map ◽  
Single Image ◽  
Low Resolution ◽  
3D Object ◽  
3D Objects ◽  
3D Object Reconstruction ◽  
Generation Network ◽  
High Resolution Reconstruction ◽  
Rgb Image

As a representative technology of artificial intelligence, 3D reconstruction based on deep learning can be integrated into the edge computing framework to form an intelligent edge and then realize the intelligent processing of the edge. Recently, high-resolution representation of 3D objects using multiview decomposition (MVD) architecture is a fast reconstruction method for generating objects with realistic details from a single RGB image. The results of high-resolution 3D object reconstruction are related to two aspects. On the one hand, a low-resolution reconstruction network represents a good 3D object from a single RGB image. On the other hand, a high-resolution reconstruction network maximizes fine low-resolution 3D objects. To improve these two aspects and further enhance the high-resolution reconstruction capabilities of the 3D object generation network, we study and improve the low-resolution 3D generation network and the depth map superresolution network. Eventually, we get an improved multiview decomposition (IMVD) network. First, we use a 2D image encoder with multifeature fusion (MFF) to enhance the feature extraction capability of the model. Second, a 3D decoder using an effective subpixel convolutional neural network (3D ESPCN) improves the decoding speed in the decoding stage. Moreover, we design a multiresidual dense block (MRDB) to optimize the depth map superresolution network, which allows the model to capture more object details and reduce the model parameters by approximately 25% when the number of network layers is doubled. The experimental results show that the proposed IMVD is better than the original MVD in the 3D object superresolution experiment and the high-resolution 3D reconstruction experiment of a single image.

Sign in / Sign up

Export Citation Format

Share Document